minerva.optimizers
==================

.. py:module:: minerva.optimizers


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/minerva/optimizers/lars/index


Classes
-------

.. autoapisummary::

   minerva.optimizers.LARS


Package Contents
----------------

.. py:class:: LARS(params, lr, momentum = 0.9, dampening = 0, weight_decay = 0.9, nesterov = False, trust_coefficient = 0.001, eps = 1e-08)

   Bases: :py:obj:`torch.optim.Optimizer`


   Implements the Layer-wise Adaptive Rate Scaling (LARS) optimizer.
   Implementation borrowed from lightly SSL library.

   Constructs a new LARS optimizer.

   Parameters
   ----------
   params : Any
       Parameters to optimize.
   lr : float
       Learning rate.
   momentum : float, optional
       Momentum factor, by default 0.9
   dampening : float, optional
       Dampening for momentum, by default 0
   weight_decay : float, optional
       Weight decay (L2 penalty), by default 0.9
   nesterov : bool, optional
       Enables Nesterov momentum, by default False
   trust_coefficient : float, optional
       Trust coefficient for computing learning rate, by default 0.001
   eps : float, optional
       Eps for division denominator, by default 1e-8



   .. py:method:: __setstate__(state)


   .. py:method:: step(closure: None = None) -> None
                  step(closure: Callable[[], float]) -> float

      Performs a single optimization step.

      Args:
          closure (callable, optional): A closure that reevaluates the model
              and returns the loss.